Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating unnecessary actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anga
    -0.18
    ew
    -0.16
    actus
    -0.16
    azzi
    -0.15
    694
    -0.15
    lege
    -0.15
    ilda
    -0.15
    ohana
    -0.14
    erb
    -0.14
    avec
    -0.14
    POSITIVE LOGITS
     Hüs
    0.17
    áno
    0.15
    AMA
    0.14
    dent
    0.14
    ardy
    0.14
    CEL
    0.14
    á»ijt
    0.14
    èħ
    0.14
    ippi
    0.13
    GES
    0.13
    Act Density 0.008%

    No Known Activations